Patents by Inventor Lianghao Chen
Lianghao Chen has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240153423Abstract: There is provided a detection circuit, a display panel and a detection method. The detection circuit includes: a conversion circuit configured to acquire a photoelectric sensing signal in real time and convert the acquired photoelectric sensing signal into a luminance value; a storage circuit configured to store N luminance values from the conversion circuit on a first input first output basis; a discrimination circuit connected to the storage circuit and configured to determine whether at least two of the N luminance values meet a preset condition; and an output circuit connected to the discrimination circuit and the storage circuit, and configured to output a preset default luminance value in response to the at least two luminance values meeting the preset condition and output at least one of the N luminance values in response to the at least two luminance values not meeting the preset condition.Type: ApplicationFiled: May 18, 2021Publication date: May 9, 2024Applicants: Beijing BOE Display Technology Co., Ltd., BOE Technology Group Co., Ltd.Inventors: Lianghao Zhang, Xinle Wang, Yifan Song, Wenchao Han, Zhaohui Meng, Wanzhi Chen, Jing Liu
-
Publication number: 20230342365Abstract: A user preference hierarchy is determined from user response to images. Images may be tagged using machine learning models trained to determine values for images. Products are clustered according to product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate affinity for a product vector. A user may provide feedback regarding a price point and products are weighted according to a distribution about the price point. The distribution may be asymmetrical according to direction of movement of the price point. Filters may be dynamically defined and presented to a user based on popularity and frequency of occurrence of attribute-value pairs of search results and based on feedback regarding the search results.Type: ApplicationFiled: June 26, 2023Publication date: October 26, 2023Applicant: The Yes Platform, Inc.Inventors: Navin Agarwal, Judy Yi-Chun Hsieh, Debbie Ayano Limongan, Lianghao Chen, Amit Aggarwal, Julie Bornstein
-
Patent number: 11727014Abstract: A user preference hierarchy is determined from user response to images. Images may be tagged using machine learning models trained to determine values for images. Products are clustered according to product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate affinity for a product vector. A user may provide feedback regarding a price point and products are weighted according to a distribution about the price point. The distribution may be asymmetrical according to direction of movement of the price point. Filters may be dynamically defined and presented to a user based on popularity and frequency of occurrence of attribute-value pairs of search results and based on feedback regarding the search results.Type: GrantFiled: December 12, 2019Date of Patent: August 15, 2023Assignee: The Yes Platform, Inc.Inventors: Navin Agarwal, Judy Yi-Chun Hsieh, Debbie Ayano Limongan, Lianghao Chen, Amit Aggarwal, Julie Bornstein
-
Patent number: 11386301Abstract: Images are tagged with values in an image data hierarchy that is most subjective at its top level and least subjective at its bottom level, such as a hierarchy including style, type, and features for clothing. A user preference hierarchy is determined from user response to images that are tagged. Tagged images may be generated by processing them with machine learning models trained to determine values for images. Product records including images and other data are analyzed to generate attribute vectors that are encoded to generate product vectors. Products are clustered according to their product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate user affinity for a product having a given product vector.Type: GrantFiled: September 6, 2019Date of Patent: July 12, 2022Assignee: The Yes PlatformInventors: Amit Aggarwal, Navin Agarwal, Judy Yi-Chun Hsieh, Lianghao Chen, Preetam Amancharla, Julie Bornstein
-
Publication number: 20210182287Abstract: A user preference hierarchy is determined from user response to images. Images may be tagged using machine learning models trained to determine values for images. Products are clustered according to product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate affinity for a product vector. A user may provide feedback regarding a price point and products are weighted according to a distribution about the price point. The distribution may be asymmetrical according to direction of movement of the price point. Filters may be dynamically defined and presented to a user based on popularity and frequency of occurrence of attribute-value pairs of search results and based on feedback regarding the search results.Type: ApplicationFiled: December 12, 2019Publication date: June 17, 2021Inventors: Navin Agarwal, Judy Yi-Chun Hsieh, Debbie Ayano Limongan, Lianghao Chen, Amit Aggarwal, Julie Bornstein
-
Publication number: 20210073593Abstract: Images are tagged with values in an image data hierarchy that is most subjective at its top level and least subjective at its bottom level, such as a hierarchy including style, type, and features for clothing. A user preference hierarchy is determined from user response to images that are tagged. Tagged images may be generated by processing them with machine learning models trained to determine values for images. Product records including images and other data are analyzed to generate attribute vectors that are encoded to generate product vectors. Products are clustered according to their product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate user affinity for a product having a given product vector.Type: ApplicationFiled: September 6, 2019Publication date: March 11, 2021Inventors: Amit Aggarwal, Navin Agarwal, Judy Yi-Chun Hsieh, Lianghao Chen, Preetam Amancharla, Julie Bornstein
-
Patent number: 8645585Abstract: A technique is disclosed for dynamically reconfiguring a digital video link based on previously determined link training parameters. Reusing the previously determined link training parameters enables a no link training (NLT) protocol for quickly configuring the digital video link without the need for repeating a link training process. A display device advertises NLT capabilities information to a GPU indicating it can retain link characteristics for one or more link configurations. The GPU uses the NLT capabilities information to determine whether the display device is able to quickly transition to a specific link configuration using the NLT protocol, or to switch between configurations. The NLT capability allows a link to be advantageously quiesced and restored quickly while the GPU is transitioning in and out of power-saving sleep states, or placing the link in a more power efficient configuration, or higher-bandwidth higher-performance configuration.Type: GrantFiled: June 10, 2011Date of Patent: February 4, 2014Assignee: NVIDIA CorporationInventors: David Wyatt, Lianghao Chen, David Matthew Stears
-
Publication number: 20120317607Abstract: A technique is disclosed for dynamically reconfiguring a digital video link based on previously determined link training parameters. Reusing the previously determined link training parameters enables a no link training (NLT) protocol for quickly configuring the digital video link without the need for repeating a link training process. A display device advertises NLT capabilities information to a GPU indicating it can retain link charactristics for one or more link configurations. The GPU uses the NLT capabilities information to determine whether the display device is able to quickly transition to a specific link configuration using the NLT protocol, or to switch between configurations. The NLT capability allows a link to be advantageously quiesced and restored quickly while the GPU is transitioning in and out of power-saving sleep states, or placing the link in a more power efficient configuration, or higher-bandwidth higher-performance configuration.Type: ApplicationFiled: June 10, 2011Publication date: December 13, 2012Inventors: David WYATT, Lianghao Chen, David Matthew Stears